© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44895
    Prev
    Next
    INDEX
    Explanations

    user profile modification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ro
    0.44
    Emulator
    0.42
    <sub>
    0.41
     roasting
    0.39
    ToObject
    0.39
     dictates
    0.38
     Emulator
    0.38
    Team
    0.38
    🆕
    0.38
    覆
    0.37
    POSITIVE LOGITS
    ালিয়া
    0.42
    枌
    0.39
    ڑا
    0.39
    ματα
    0.38
     잠
    0.38
    igamma
    0.38
     Pennington
    0.38
     comprim
    0.38
     perdita
    0.38
    mtr
    0.37
    Activations Density 0.002%

    No Known Activations